Using Principal Component Analysis to Recognize Farsi Alphabetic Characters in Printed Scripts

Document Type : Original Article(s)

Authors

1 Department of Medical Physics and Engineering, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

2 Associate Professor, Department of Medical Physics and Engineering, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

3 Assistant Professor, Department of Medical Physics and Engineering, School of Medicine AND Medical Signal and Image Research Center, Isfahan University of Medical Sciences, Isfahan, Iran

Abstract

Background: From the early stages of script writing and reading, there was a big desire for researchers to make an aid device for the blind to read scripts without help of other. This paper introduced a new approach for recognition of Farsi scripts using principal component analysis (PCA).Methods: Materials used for this project were selected from ordinary books, magazines, newspapers, and printed documents. Character samples were selected from four fonts in different positions and three sizes resulted in total number of 20 recognition classes. The five methods used in character recognition were statistical method, Fast Zernike Wavelet Moments (FZWM) method, PCA, PCA with sample averaging, and PCA with eigenvectors averaging.Findings: The accuracy and speed of PCA in recognition of Farsi characters were respectively 1.775% and 7.5 times better than the statistical method. Likewise, it was 2.2% more accurate and 5.12 times faster than FZWM method. Conclusion: Using PCA with combinational averaging in samples and eigenvectors can be a novel method for recognition of Farsi characters.

Keywords

References

  1. Parslow A. An optical real-world text to speech reader. International Congress Series 2005; 1282: 1056-60.
  2. Fazilat M. Applied technology for blinds. Electronic Edition of Documents and Information of Iran 2007; 1(7): 1-7.
  3. Amin A. Machine recognition of handwritten Arabic words by IRAC II. Proceedings of the 6th International Conference in Pattern Recognition; 1982 Oct; Munich, Germany. p. 729-31.
  4. Amin A, Masini G, Haton JP. Recognition of Arabic words and sentences. Proceedings of the 7th International Conference in Pattern Recognition; 1984; Montreal, Canada. p. 1055-7.
  5. Badi K, Shimura M. Machine recognition of Arabic cursive scripts. Trans Inst Electron Commun Eng 1982; E65(2): 107-14.
  6. Amin A, Masini G. Machine recognition of multifont printed Arabic texts. Proceedings of the 8th International Conference in Pattern Recognition; 1986 Oct 27-31; Paris, France. p. 392-95.
  7. Hachour O. The combination of fuzzy logic and expert system for Arabic character recognition. Proceedings of the 3rd International IEEE Conference on Intelligent Systems; 2006; p. 189-91.
  8. Hashemi MR, Fatemi O, Safavi R. Persian cursive script recognition. Proceedings of the 3rd International Conference on pattern recognition; 1995 Aug 14-16; Montreal, Canada. p. 869-73.
  9. Broumandnia A, Shanbehzadeh J. Fast zernike wavelet moments for Farsi character recognition. Image and Vision Computing 2007; 25(5): 717-26.
  10. Curado LAF, Bauchspiess A, CuradoVBF. Using PCA to recognize characters in vehicle license plates. Proceedings of the World Congress in Computer Science; 2006; Las Vegas, USA. p. 264-68.
  11. Kubba GA. The impact of computers on Arabic writing, character processing and teaching. Proceedings of I.F.I.P. Congress on Information Processing and Education (Area 9); 1980 Oct; Tokyo, Japan. p. 961-65.
  12. Shlens J. A Tutorial on principal component analysis: derivation, discussion and singular value decomposition. [Online] 2006 Available from: URL: http://www.snl.salk.edu/~shlens/notes.html.
  13. Haykin S. Neural network: a comprehensive foundation. 2nd ed. Englewood Cliffs, NJ: Prentice Hall; 1999.
  14. Turk M, Pentland A. Eigenfaces for recognition. Journal of Cognitive Neuroscience 1991; 3(1): 71-86.
  15. Silva P, Rosa A. Face recognition based on symmetryzation. Centre for Secure Information Technologies. [Online] 2002. Available from: URL: http//www.wenku.baidu.com/view/8cf86cc558f5f61fb7366610.html.
  16. Chong CW, Raveendran P, Mukundan R. Translation invariants of Zernike moments. The Journal of the Pattern Recognition Society 2003; 36: 1765-73.
  17. Chim YC KAIY. Character recognition using statistical moments. Image and Vision Computing 1999; 17: 299-307.
  18. Mallat S. A Wavelet Tour of Signal Processing. 2nd ed. New York, NY: Academic Press; 1999.
Journal of Isfahan Medical School
Volume 29, Issue 174 - Serial Number 174
November and December 2011
Pages 3211-3220

Files

History

  • Receive Date: 05 May 2012
  • Revise Date:
  • Accept Date: 06 April 2022

Share

How to cite

Statistics